Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0000

Data Index: 203927 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1573693 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1487125 (Python Code)

Max Activating Token Index: 946

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0871. Min Act: -0.0000

Data Index: 92955 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0778. Min Act: -0.0000

Data Index: 904080 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0740. Min Act: -0.0000

Data Index: 527108 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1234912 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0627. Min Act: -0.0000

Data Index: 945660 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0682. Min Act: -0.0000

Data Index: 761874 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1192559 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1130087 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0629. Min Act: -0.0000

Data Index: 125084 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1450503 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1059466 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0575. Min Act: -0.0000

Data Index: 384533 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1335366 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0634. Min Act: -0.0000

Data Index: 204882 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0549. Min Act: -0.0000

Data Index: 991419 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0595. Min Act: -0.0000

Data Index: 661637 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1262442 (C4 (Web Text))

Max Activating Token Index: 463